A 3D Lung Nodule Candidate Detection by Grouping DCNN 2D Candidates

Fernando Pereira, David Menotti, Lucas Ferrari de Oliveira

Abstract

Lung cancer has attracted the attention of scientific communities as being the main causes of morbidity and mortality worldwide. Computed Tomography (CT) scan is highly indicated to detect patterns such as lung nodules, where their correct detection and accurate classification is paramount for clinical decision-making. In this paper, we propose a two-step method for lung nodule candidate detection using a Deep Convolutional Neural Network (DCNN), more specifically the Single Shot MultiBox Detector, for candidate detection in 2D images/slices, and then a fusion technique to group the inter-slice adjacent detected candidates. The DCNN system was trained and validated with data from Lung Image Database Consortium and Image Database Resource Initiative, we also use LUng Nodule Analysis 2016 challenge data and metrics to evaluate the system. We had as result sensitivity of 96.7% and an average of 77.4 False Positives (FPs) per scan (an entire set of CT images/slices for a patient). The sensitivity result is ranking two in the state of art (rank one is 97.1%) but with FPs/scan rate which is almost three times smaller than the first one (219.1).

Download


Paper Citation


in Harvard Style

Pereira F., Menotti D. and Ferrari de Oliveira L. (2019). A 3D Lung Nodule Candidate Detection by Grouping DCNN 2D Candidates.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-354-4, pages 537-544. DOI: 10.5220/0007398705370544


in Bibtex Style

@conference{visapp19,
author={Fernando Pereira and David Menotti and Lucas Ferrari de Oliveira},
title={A 3D Lung Nodule Candidate Detection by Grouping DCNN 2D Candidates},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2019},
pages={537-544},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007398705370544},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - A 3D Lung Nodule Candidate Detection by Grouping DCNN 2D Candidates
SN - 978-989-758-354-4
AU - Pereira F.
AU - Menotti D.
AU - Ferrari de Oliveira L.
PY - 2019
SP - 537
EP - 544
DO - 10.5220/0007398705370544